ML based Prototype for Skin Cancer Detection

Abstract

Skin malignant growth is one of the most lethal types of disease, and the demise rate has essentially become because of an absence of consciousness of the markers and protection measures. Therefore, in order to stop the spread of cancer, early identification at an early stage is essential. Skin cancer is further classified into several forms, with melanoma, nevus and seborrheic_keratosis. This study utilizes Artificial Intelligence (AI) and picture-handling techniques to recognize and classify various types of skin cancer. Dermoscopic pictures are thought about as contributions during the pre-handling steps. The production of a Convolutional Neural Network based melanoma detection model. If melanoma is not found in its early stages, it can be fatal. It is responsible for 75% of skin cancer fatalities. A system that can analyse photos and notify dermatologists of the existence of melanoma might potentially eliminate the need for a lot of manual diagnosis work. Similar findings to those of the pertained model were produced by our created model. In simulations using the 2017 International Skin Imaging Collaboration skin cancer dataset, the suggested method performed admirably. The Convolutional neural network was able to achieve a 92 % accuracy rate.